{"id":"https://openalex.org/W1598442403","doi":"https://doi.org/10.21437/icslp.2002-200","title":"A trainable spoken language understanding system for visual object selection","display_name":"A trainable spoken language understanding system for visual object selection","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1598442403","doi":"https://doi.org/10.21437/icslp.2002-200","mag":"1598442403"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deb Roy","raw_affiliation_strings":["The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142"],"affiliations":[{"raw_affiliation_string":"The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008267833","display_name":"Peter Gorniak","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Gorniak","raw_affiliation_strings":["The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142"],"affiliations":[{"raw_affiliation_string":"The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103287143","display_name":"Niloy Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niloy Mukherjee","raw_affiliation_strings":["The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142"],"affiliations":[{"raw_affiliation_string":"The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5096860445","display_name":"Josh Juster","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Juster","raw_affiliation_strings":["The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142"],"affiliations":[{"raw_affiliation_string":"The Media Laboratory Massachusetts Institute of Technology 20 Ames Street, Cambridge, MA 02142","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004281470"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.1857,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9488107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"593","last_page":"596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7890057563781738},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.64119553565979},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.6113348007202148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6022281050682068},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5986096858978271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888664722442627},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44772157073020935},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4200073182582855},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2315792441368103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890057563781738},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.64119553565979},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.6113348007202148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6022281050682068},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5986096858978271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888664722442627},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44772157073020935},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4200073182582855},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2315792441368103},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2002-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.6088","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.6088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.media.mit.edu/cogmac/publications/newt_icslp02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.4953","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.4953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.media.mit.edu/~dkroy/papers/pdf/roy_gorniak_niloy_2002.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1571931074","https://openalex.org/W1934863104","https://openalex.org/W2060491487","https://openalex.org/W2140732660","https://openalex.org/W2141713975","https://openalex.org/W2156050092","https://openalex.org/W3128655779"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W2333383158"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,12,17,34,42,55,67,87,94],"trainable,":[3],"visually-grounded,":[4],"spoken":[5,72,134],"language":[6],"understanding":[7],"system.":[8,53,110],"The":[9,29,78,111],"system":[10,30,59,100,112],"acquires":[11],"grammar":[13],"and":[14,82,90,114,119],"vocabulary":[15,89],"from":[16],"&amp;quot;show-and-tell&amp;quot;":[18],"procedure":[19],"in":[20,33,48,63,106,121],"which":[21,126],"visual":[22,130],"scenes":[23],"are":[24,80],"paired":[25],"with":[26,98],"verbal":[27],"descriptions.":[28],"is":[31,46],"embodied":[32],"table-top":[35],"mounted":[36],"active":[37],"vision":[38,52],"platform.":[39],"During":[40],"training,":[41],"set":[43],"of":[44,50,74,108,132],"objects":[45,62,104],"placed":[47,105],"front":[49,107],"the":[51,58,75,99,109,117,124,129,133],"Using":[54],"laser":[56],"pointer,":[57],"points":[60],"to":[61,70,84,123],"random":[64],"sequence,":[65],"prompting":[66],"human":[68],"teacher":[69],"provide":[71],"descriptions":[73,79],"selected":[76],"objects.":[77],"transcribed":[81],"used":[83],"automatically":[85],"acquire":[86],"visually-grounded":[88],"grammar.":[91],"Once":[92],"trained,":[93],"person":[95],"can":[96],"interact":[97],"by":[101],"verbally":[102],"describing":[103],"recognizes":[113],"robustly":[115],"parses":[116],"speech":[118],"points,":[120],"real-time,":[122],"object":[125],"best":[127],"fits":[128],"semantics":[131],"description.":[135],"1.":[136]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
